© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17174
    Prev
    Next
    INDEX
    Explanations

    personal guarantor

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign "but" or etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ort
    0.46
    ir
    0.44
     webpages
    0.43
    ,
    0.41
     captivated
    0.40
    ne
    0.40
     ample
    0.40
    ki
    0.38
     instantaneous
    0.38
     neckline
    0.38
    POSITIVE LOGITS
     stockbild
    0.54
     अल्को
    0.54
    তবে
    0.52
     jedoch
    0.52
     政
    0.50
    爫
    0.49
     سیاست
    0.49
     pédagog
    0.49
     αλλά
    0.48
     Catawiki
    0.48
    Activations Density 0.000%

    No Known Activations